© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 91955
    Prev
    Next
    INDEX
    Explanations

    launch success and failures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menus
    0.54
    Leaves
    0.49
     \
    0.48
     breaths
    0.46
     बदल
    0.46
     ferment
    0.46
     clubhouse
    0.46
     advertise
    0.45
    Advertise
    0.45
    Breath
    0.45
    POSITIVE LOGITS
    بي
    0.59
    計測
    0.54
     ಸ್ಥಳ
    0.52
    耧
    0.51
     deuxième
    0.51
    UAL
    0.50
    ている
    0.50
    به
    0.49
     steeds
    0.49
    čina
    0.49
    Activations Density 0.037%

    No Known Activations